Instructions to use diffusion-reasoning/gdsd_countdown_llada with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use diffusion-reasoning/gdsd_countdown_llada with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="diffusion-reasoning/gdsd_countdown_llada", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("diffusion-reasoning/gdsd_countdown_llada", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use diffusion-reasoning/gdsd_countdown_llada with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "diffusion-reasoning/gdsd_countdown_llada"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "diffusion-reasoning/gdsd_countdown_llada",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/diffusion-reasoning/gdsd_countdown_llada

SGLang

How to use diffusion-reasoning/gdsd_countdown_llada with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "diffusion-reasoning/gdsd_countdown_llada" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "diffusion-reasoning/gdsd_countdown_llada",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "diffusion-reasoning/gdsd_countdown_llada" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "diffusion-reasoning/gdsd_countdown_llada",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use diffusion-reasoning/gdsd_countdown_llada with Docker Model Runner:
```
docker model run hf.co/diffusion-reasoning/gdsd_countdown_llada
```

gdsd_countdown_llada / model.safetensors.index.json

jky594176

Upload merged LLaDA model with sudoku reasoning capabilities

cabe4a5 verified 16 days ago

raw

history blame contribute delete

25 kB

	{
	"metadata": {
	"total_parameters": 8015581184,
	"total_size": 16031162368
	},
	"weight_map": {
	"model.transformer.blocks.0.attn_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.0.attn_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.0.ff_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.0.ff_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.0.ff_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.0.k_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.0.q_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.0.up_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.0.v_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.1.attn_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.1.attn_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.1.ff_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.1.ff_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.1.ff_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.1.k_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.1.q_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.1.up_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.1.v_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.10.attn_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.10.attn_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.10.ff_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.10.ff_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.10.ff_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.10.k_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.10.q_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.10.up_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.10.v_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.11.attn_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.11.attn_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.11.ff_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.11.ff_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.11.ff_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.11.k_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.11.q_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.11.up_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.11.v_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.12.attn_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.12.attn_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.12.ff_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.12.ff_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.12.ff_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.12.k_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.12.q_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.12.up_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.12.v_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.13.attn_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.13.attn_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.13.ff_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.13.ff_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.13.ff_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.13.k_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.13.q_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.13.up_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.13.v_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.14.attn_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.14.attn_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.14.ff_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.14.ff_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.14.ff_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.14.k_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.14.q_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.14.up_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.14.v_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.15.attn_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.15.attn_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.15.ff_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.15.ff_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.15.ff_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.15.k_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.15.q_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.15.up_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.15.v_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.16.attn_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.16.attn_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.16.ff_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.16.ff_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.16.ff_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.16.k_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.16.q_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.16.up_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.16.v_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.17.attn_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.17.attn_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.17.ff_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.17.ff_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.17.ff_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.17.k_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.17.q_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.17.up_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.17.v_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.18.attn_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.18.attn_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.18.ff_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.18.ff_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.18.ff_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.18.k_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.18.q_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.18.up_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.18.v_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.19.attn_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.19.attn_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.19.ff_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.19.ff_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.19.ff_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.19.k_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.19.q_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.19.up_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.19.v_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.2.attn_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.2.attn_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.2.ff_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.2.ff_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.2.ff_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.2.k_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.2.q_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.2.up_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.2.v_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.20.attn_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.20.attn_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.20.ff_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.20.ff_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.20.ff_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.20.k_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.20.q_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.20.up_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.20.v_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.21.attn_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.21.attn_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.21.ff_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.21.ff_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.21.ff_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.21.k_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.21.q_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.21.up_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.21.v_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.22.attn_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.22.attn_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.22.ff_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.22.ff_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.22.ff_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.22.k_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.22.q_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.22.up_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.22.v_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.23.attn_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.23.attn_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.23.ff_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.23.ff_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.23.ff_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.23.k_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.23.q_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.23.up_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.23.v_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.24.attn_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.24.attn_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.24.ff_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.24.ff_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.24.ff_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.24.k_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.24.q_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.24.up_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.24.v_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.25.attn_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.25.attn_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.25.ff_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.25.ff_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.25.ff_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.25.k_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.25.q_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.25.up_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.25.v_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.26.attn_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.26.attn_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.26.ff_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.26.ff_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.26.ff_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.26.k_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.26.q_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.26.up_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.26.v_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.27.attn_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.27.attn_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.27.ff_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.27.ff_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.27.ff_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.27.k_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.27.q_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.27.up_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.27.v_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.28.attn_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.28.attn_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.28.ff_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.28.ff_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.28.ff_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.28.k_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.28.q_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.28.up_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.28.v_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.29.attn_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.29.attn_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.29.ff_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.29.ff_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.29.ff_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.29.k_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.29.q_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.29.up_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.29.v_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.3.attn_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.3.attn_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.3.ff_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.3.ff_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.3.ff_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.3.k_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.3.q_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.3.up_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.3.v_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.30.attn_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.30.attn_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.30.ff_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.30.ff_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.30.ff_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.30.k_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.30.q_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.30.up_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.30.v_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.31.attn_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.31.attn_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.31.ff_norm.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.31.ff_out.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.31.ff_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.31.k_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.31.q_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.31.up_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.31.v_proj.weight": "model-00003-of-00004.safetensors",
	"model.transformer.blocks.4.attn_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.4.attn_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.4.ff_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.4.ff_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.4.ff_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.4.k_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.4.q_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.4.up_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.4.v_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.5.attn_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.5.attn_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.5.ff_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.5.ff_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.5.ff_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.5.k_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.5.q_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.5.up_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.5.v_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.6.attn_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.6.attn_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.6.ff_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.6.ff_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.6.ff_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.6.k_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.6.q_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.6.up_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.6.v_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.7.attn_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.7.attn_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.7.ff_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.7.ff_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.7.ff_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.7.k_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.7.q_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.7.up_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.7.v_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.8.attn_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.8.attn_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.8.ff_norm.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.8.ff_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.8.ff_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.8.k_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.8.q_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.8.up_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.8.v_proj.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.9.attn_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.9.attn_out.weight": "model-00001-of-00004.safetensors",
	"model.transformer.blocks.9.ff_norm.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.9.ff_out.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.9.ff_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.9.k_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.9.q_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.9.up_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.blocks.9.v_proj.weight": "model-00002-of-00004.safetensors",
	"model.transformer.ff_out.weight": "model-00004-of-00004.safetensors",
	"model.transformer.ln_f.weight": "model-00001-of-00004.safetensors",
	"model.transformer.wte.weight": "model-00001-of-00004.safetensors"
	}
	}